© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16001
    Prev
    Next
    INDEX
    Explanations

    "TR", "BL", "BR", "ML", "MM", "TM", "BM"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.07
    ↵
    -0.06
    orro
    -0.06
    ÏĨÏĮ
    -0.06
    èĢĮä¸Ķæĺ¯
    -0.06
    ئت
    -0.06
    绣èĢĥ
    -0.06
    anged
    -0.06
    tä
    -0.06
     rogue
    -0.05
    POSITIVE LOGITS
     enfin
    0.12
     infine
    0.11
     ë§Īì§Ģë§īìľ¼ë¡ľ
    0.09
    åħ¶ä½Ļ
    0.09
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.09
    æľĢåIJİæĺ¯
    0.09
    俱ä¹IJéĥ¨
    0.09
     наконеÑĨ
    0.09
     finally
    0.09
    สุà¸Ķà¸Ĺà¹īาย
    0.09
    Activations Density 0.106%

    No Known Activations